Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ELECTROCARDIOGRAM GENERATION DEVICE BASED ON GENERATIVE ADVERSARIAL NETWORK ALGORITHM, AND METHOD THEREOF
Document Type and Number:
WIPO Patent Application WO/2022/014943
Kind Code:
A1
Abstract:
The present invention relates to an electrocardiogram generation device based on a generative adversarial network algorithm, and a method thereof. The electrocardiogram generation device based on a generative adversarial network algorithm, according to the present invention, comprises: an input unit for receiving electrocardiogram data of a patient who is to be diagnosed for symptoms; a control unit for generating a plurality of synthesized electrocardiogram data by inputting the received electrocardiogram data into a pre-trained generative adversarial network algorithm; and an output unit for outputting the received actual electrocardiogram data of the patient and the plurality of generated electrocardiogram data. As such, according to the present invention, electrocardiogram data is learned according to each characteristic by using a deep learning algorithm, and thus accuracy in diagnosing an arrhythmia, which is a type of heart disease, increases by using a trained model for the diagnosis, and diagnostic reliability may increase since the reasons for the arrhythmia diagnosis may also be presented.

Inventors:
KWON JOON MYOUNG (KR)
Application Number:
PCT/KR2021/008627
Publication Date:
January 20, 2022
Filing Date:
July 07, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
BODYFRIEND CO LTD (KR)
MEDICAL AI (KR)
International Classes:
A61B5/327; A61B5/00; A61B5/349; G06N3/08; G16H50/20
Foreign References:
JP2005323821A2005-11-24
KR20190114694A2019-10-10
JP2020042598A2020-03-19
KR102078703B12020-02-19
KR101109738B12012-02-24
Other References:
KIM, MIN-GU; PAN, SUNG BUM: "A Sudy on Simulated ECG Generation of GAN based using Axiliary Cassifier", PROCEEDINGS OF KIIT CONFERENCE, 1 January 2019 (2019-01-01), Korea, pages 120 - 121, XP009533428
See also references of EP 4162876A4
Download PDF: